Most works on person re-identification (ReID) take advantage of large backbone networks
such as ResNet, which are designed for image classification instead of ReID, for feature …

Many deep learning models, developed in recent years, reach higher ImageNet accuracy
than ResNet50, with fewer or comparable FLOPs count. While FLOPs are often seen as a …

Person Re-Identification aims to retrieve person identities from images captured by multiple
cameras or the same cameras in different time instances and locations. Because of its …

Effective metric learning is important in various applications, especially for re-identification.
Compared with most existing re-identification methods which are not suitable for a real-time …

Recent works in the person re-identification task mainly focus on the model accuracy while
ignoring factors related to efficiency, eg, model size and latency, which are critical for …

This study aims to leverage Binary Neural Networks (BNN) to learn binary hash codes for
efficient person re-identification (ReID). BNNs, which use binary weights and activations …

In this paper, we propose a new collaborative consistency learning method for person ReID
that improves generalization and robustness to label noise without introducing additional …

Partial person ReID tasks have become a research focus recently for it is challenging but
significant in practical applications. The major difficulty within partial person ReID is that only …

Multi-task learning demonstrates excellent performance in multiple domains of deep
learning. Nevertheless, how to obtain knowledge beneficial to each task from the shared …